{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:19:12Z","timestamp":1784215152322,"version":"3.55.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62088102"],"award-info":[{"award-number":["62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62125305"],"award-info":[{"award-number":["62125305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U23A20339"],"award-info":[{"award-number":["U23A20339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62203348"],"award-info":[{"award-number":["62203348"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tnnls.2024.3443102","type":"journal-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T17:25:43Z","timestamp":1726853143000},"page":"11215-11227","source":"Crossref","is-referenced-by-count":9,"title":["Improving Offline Reinforcement Learning With in-Sample Advantage Regularization for Robot Manipulation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0835-4356","authenticated-orcid":false,"given":"Chengzhong","family":"Ma","sequence":"first","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deyu","family":"Yang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Wu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3110-8618","authenticated-orcid":false,"given":"Zeyang","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houxue","family":"Yang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5226-963X","authenticated-orcid":false,"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3422-944X","authenticated-orcid":false,"given":"Xuguang","family":"Lan","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1608-8257","authenticated-orcid":false,"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref3","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2852711"},{"key":"ref5","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16579"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwad037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref12","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto"},{"key":"ref13","first-page":"11761","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref14","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref15","article-title":"Mildly conservative Q-learning for offline reinforcement learning","author":"Lyu","year":"2022","journal-title":"arXiv:2206.04745"},{"key":"ref16","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref17","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An"},{"key":"ref18","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","author":"Bai","year":"2022","journal-title":"arXiv:2202.11566"},{"key":"ref19","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref20","first-page":"4933","article-title":"Offline RL without off-policy evaluation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Brandfonbrener"},{"key":"ref21","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945019"},{"key":"ref24","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau"},{"key":"ref25","first-page":"31278","article-title":"Supported policy optimization for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wu"},{"key":"ref26","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref27","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv:2006.09359"},{"key":"ref28","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv:1910.00177"},{"key":"ref29","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref30","first-page":"23851","article-title":"RORL: Robust offline reinforcement learning via conservative smoothing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yang"},{"key":"ref31","first-page":"5774","article-title":"Offline reinforcement learning with Fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref32","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref33","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref34","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"Wu","year":"2021","journal-title":"arXiv:2105.08140"},{"key":"ref35","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Janner"},{"key":"ref36","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref37","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021","journal-title":"arXiv:2108.03298"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref40","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3166993"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3248324"},{"key":"ref44","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref49","first-page":"6291","article-title":"Exponentially weighted imitation learning for batched historical data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref51","article-title":"Policy regularization with dataset constraint for offline reinforcement learning","author":"Ran","year":"2023","journal-title":"arXiv:2306.06569"},{"key":"ref52","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"issue":"11","key":"ref53","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref55","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref56","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref57","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref58","article-title":"Offline RL with no OOD actions: In-sample learning via implicit value regularization","author":"Xu","year":"2023","journal-title":"arXiv:2303.15810"},{"key":"ref59","article-title":"Learning to reach goals via iterated supervised learning","author":"Ghosh","year":"2019","journal-title":"arXiv:1912.06088"},{"key":"ref60","article-title":"Rethinking goal-conditioned supervised learning and its connection to offline RL","author":"Yang","year":"2022","journal-title":"arXiv:2202.04478"},{"key":"ref61","first-page":"5150","article-title":"Towards human-level bimanual dexterous manipulation with reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chen"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3238910"},{"key":"ref64","article-title":"When data geometry meets deep function: Generalizing offline reinforcement learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Li"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10684782.pdf?arnumber=10684782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:58:30Z","timestamp":1749059910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":64,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3443102","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}